Refresh gate action mirror release evidence
This commit is contained in:
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-16T21:16:12Z",
|
||||
"generated_at": "2026-06-17",
|
||||
"skill_dir": ".",
|
||||
"source_patterns": "reports/user_patterns.json",
|
||||
"pattern_count": 5,
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Adaptation Proposals
|
||||
|
||||
- Generated at: `2026-06-16T21:16:12Z`
|
||||
- Generated at: `2026-06-17`
|
||||
- Pattern report: `reports/user_patterns.json`
|
||||
- Proposal only: `true`
|
||||
- Writes repository files: `false`
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"ok": true,
|
||||
"schema_version": "2.0",
|
||||
"generated_at": "2026-06-16T21:16:41Z",
|
||||
"generated_at": "2026-06-16T21:18:14Z",
|
||||
"skill_dir": ".",
|
||||
"privacy_contract": {
|
||||
"storage": "local-first",
|
||||
|
||||
@@ -3,49 +3,43 @@
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-17",
|
||||
"skill_dir": ".",
|
||||
"commit": "7050664b482a8ed9ff8d763f08800902fdf1f02d",
|
||||
"commit": "cd71fd61e4d1c8db758ac0d2e9d1873a5a4ef547",
|
||||
"git_status": {
|
||||
"available": true,
|
||||
"dirty": true,
|
||||
"changed_file_count": 39,
|
||||
"changed_file_count": 15,
|
||||
"generated_dirty": true,
|
||||
"generated_changed_file_count": 34,
|
||||
"source_dirty": true,
|
||||
"source_changed_file_count": 5,
|
||||
"generated_changed_file_count": 15,
|
||||
"source_dirty": false,
|
||||
"source_changed_file_count": 0,
|
||||
"sample": [
|
||||
" M registry/index.json",
|
||||
" M registry/packages/yao-meta-skill.json",
|
||||
" M reports/adaptation_proposals.json",
|
||||
" M reports/adaptation_proposals.md",
|
||||
" M reports/adoption_drift_report.json",
|
||||
" M reports/architecture_maintainability.json",
|
||||
" M reports/architecture_maintainability.md",
|
||||
" M reports/benchmark_reproducibility.json",
|
||||
" M reports/benchmark_reproducibility.md",
|
||||
" M reports/context_budget.json",
|
||||
" M reports/context_budget.md",
|
||||
" M reports/context_budget_summary.json"
|
||||
],
|
||||
"source_sample": [
|
||||
" M scripts/render_evidence_consistency.py",
|
||||
" M scripts/render_review_studio.py",
|
||||
" M scripts/review_studio_actions.py",
|
||||
" M tests/verify_evidence_consistency.py",
|
||||
" M tests/verify_review_studio.py"
|
||||
" M reports/evidence_consistency.json",
|
||||
" M reports/output_execution_runs.json",
|
||||
" M reports/output_execution_runs.md",
|
||||
" M reports/review-studio.html",
|
||||
" M reports/review-studio.json",
|
||||
" M reports/review-viewer.json",
|
||||
" M reports/skill-interpretation.json"
|
||||
],
|
||||
"source_sample": [],
|
||||
"generated_sample": [
|
||||
" M registry/index.json",
|
||||
" M registry/packages/yao-meta-skill.json",
|
||||
" M reports/adaptation_proposals.json",
|
||||
" M reports/adaptation_proposals.md",
|
||||
" M reports/adoption_drift_report.json",
|
||||
" M reports/architecture_maintainability.json",
|
||||
" M reports/architecture_maintainability.md",
|
||||
" M reports/benchmark_reproducibility.json",
|
||||
" M reports/benchmark_reproducibility.md",
|
||||
" M reports/context_budget.json",
|
||||
" M reports/context_budget.md",
|
||||
" M reports/context_budget_summary.json"
|
||||
" M reports/evidence_consistency.json",
|
||||
" M reports/output_execution_runs.json",
|
||||
" M reports/output_execution_runs.md",
|
||||
" M reports/review-studio.html",
|
||||
" M reports/review-studio.json",
|
||||
" M reports/review-viewer.json",
|
||||
" M reports/skill-interpretation.json"
|
||||
],
|
||||
"generated_dirty_prefixes": [
|
||||
"dist/",
|
||||
@@ -59,11 +53,11 @@
|
||||
},
|
||||
"summary": {
|
||||
"reproducibility_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"methodology_complete": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"evidence_bundle_sha256": "c31e8bd9e49e60f14344e25ae71dabf911612d9c1ae6aee292ce566c66b88fce",
|
||||
"evidence_bundle_sha256": "b29129730b143a8ee3e8f3976ea953ed7173e0c7de9c4e8a2fc2f4c47635fe15",
|
||||
"source_contract_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
|
||||
"output_case_count": 5,
|
||||
@@ -83,19 +77,18 @@
|
||||
"world_class_source_pass_count": 10,
|
||||
"world_class_source_blocked_count": 9,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 5,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 39,
|
||||
"source_tree_dirty": true,
|
||||
"source_changed_file_count": 5,
|
||||
"changed_file_count": 15,
|
||||
"source_tree_dirty": false,
|
||||
"source_changed_file_count": 0,
|
||||
"generated_tree_dirty": true,
|
||||
"generated_changed_file_count": 34
|
||||
"generated_changed_file_count": 15
|
||||
},
|
||||
"public_claim": {
|
||||
"ready": false,
|
||||
"scope": "public benchmark or world-class readiness claim",
|
||||
"blockers": [
|
||||
"release lock is not clean or commit is unavailable",
|
||||
"provider-backed model holdout evidence is incomplete",
|
||||
"human blind-review adjudication is incomplete",
|
||||
"world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)",
|
||||
@@ -104,12 +97,12 @@
|
||||
"policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, accepted world-class evidence, and complete source checks."
|
||||
},
|
||||
"release_lock": {
|
||||
"ready": false,
|
||||
"commit": "7050664b482a8ed9ff8d763f08800902fdf1f02d",
|
||||
"ready": true,
|
||||
"commit": "cd71fd61e4d1c8db758ac0d2e9d1873a5a4ef547",
|
||||
"status_scope": "generation-time status before this report is written",
|
||||
"source_changed_file_count": 5,
|
||||
"generated_changed_file_count": 34,
|
||||
"reason": "source files were dirty at generation time"
|
||||
"source_changed_file_count": 0,
|
||||
"generated_changed_file_count": 15,
|
||||
"reason": "only generated evidence artifacts were dirty at generation time"
|
||||
},
|
||||
"evidence_bundle": {
|
||||
"algorithm": "sha256(path,label,exists,artifact_sha256)",
|
||||
@@ -117,7 +110,7 @@
|
||||
"existing_count": 25,
|
||||
"missing_count": 0,
|
||||
"missing_paths": [],
|
||||
"sha256": "c31e8bd9e49e60f14344e25ae71dabf911612d9c1ae6aee292ce566c66b88fce"
|
||||
"sha256": "b29129730b143a8ee3e8f3976ea953ed7173e0c7de9c4e8a2fc2f4c47635fe15"
|
||||
},
|
||||
"methodology": {
|
||||
"path": "reports/benchmark_methodology.md",
|
||||
@@ -190,8 +183,8 @@
|
||||
"label": "output_execution",
|
||||
"path": "reports/output_execution_runs.json",
|
||||
"exists": true,
|
||||
"bytes": 7966,
|
||||
"sha256": "9d1dbd75c98b75a63c4c7e3ae4175274a9d54e33fd1ca73561deb4dbc0b315ed"
|
||||
"bytes": 7965,
|
||||
"sha256": "db2564dbc622814ae57e8459d2a241b0f76fbf78f00af1d484ca5cdaa3265cae"
|
||||
},
|
||||
{
|
||||
"label": "blind_review",
|
||||
|
||||
@@ -1,16 +1,16 @@
|
||||
# Benchmark Reproducibility
|
||||
|
||||
Generated at: `2026-06-17`
|
||||
Commit: `7050664b482a8ed9ff8d763f08800902fdf1f02d`
|
||||
Commit: `cd71fd61e4d1c8db758ac0d2e9d1873a5a4ef547`
|
||||
Working tree dirty at generation: `true`
|
||||
Source tree dirty at generation: `true`
|
||||
Source tree dirty at generation: `false`
|
||||
Generated evidence dirty at generation: `true`
|
||||
Evidence bundle SHA256: `c31e8bd9e49e60f14344e25ae71dabf911612d9c1ae6aee292ce566c66b88fce`
|
||||
Evidence bundle SHA256: `b29129730b143a8ee3e8f3976ea953ed7173e0c7de9c4e8a2fc2f4c47635fe15`
|
||||
|
||||
## Summary
|
||||
|
||||
- reproducibility ready: `true`
|
||||
- release lock ready: `false`
|
||||
- release lock ready: `true`
|
||||
- methodology complete: `true`
|
||||
- required artifacts: `25`
|
||||
- missing artifacts: `0`
|
||||
@@ -24,10 +24,10 @@ Evidence bundle SHA256: `c31e8bd9e49e60f14344e25ae71dabf911612d9c1ae6aee292ce566
|
||||
- world-class ready: `false`
|
||||
- world-class source checks: `10` pass / `19` total; `9` blocked
|
||||
- public claim ready: `false`
|
||||
- public claim blockers: `5`
|
||||
- changed files at generation: `39`
|
||||
- source changed files at generation: `5`
|
||||
- generated changed files at generation: `34`
|
||||
- public claim blockers: `4`
|
||||
- changed files at generation: `15`
|
||||
- source changed files at generation: `0`
|
||||
- generated changed files at generation: `15`
|
||||
|
||||
This report proves local benchmark reproducibility only. It keeps external provider and human-review gaps visible instead of counting them as complete. The git commit and dirty samples are generation-time context; the evidence bundle SHA is the durable anchor for the artifacts listed below.
|
||||
|
||||
@@ -39,7 +39,6 @@ This report proves local benchmark reproducibility only. It keeps external provi
|
||||
|
||||
| Blocker |
|
||||
| --- |
|
||||
| release lock is not clean or commit is unavailable |
|
||||
| provider-backed model holdout evidence is incomplete |
|
||||
| human blind-review adjudication is incomplete |
|
||||
| world-class evidence is not accepted yet (4 open gaps, 4 ledger pending) |
|
||||
@@ -47,15 +46,15 @@ This report proves local benchmark reproducibility only. It keeps external provi
|
||||
|
||||
## Release Lock
|
||||
|
||||
- ready: `false`
|
||||
- reason: source files were dirty at generation time
|
||||
- ready: `true`
|
||||
- reason: only generated evidence artifacts were dirty at generation time
|
||||
- status scope: generation-time status before this report is written
|
||||
|
||||
## Evidence Bundle
|
||||
|
||||
- algorithm: `sha256(path,label,exists,artifact_sha256)`
|
||||
- artifacts: `25` / `25`
|
||||
- sha256: `c31e8bd9e49e60f14344e25ae71dabf911612d9c1ae6aee292ce566c66b88fce`
|
||||
- sha256: `b29129730b143a8ee3e8f3976ea953ed7173e0c7de9c4e8a2fc2f4c47635fe15`
|
||||
|
||||
## Methodology Sections
|
||||
|
||||
@@ -77,7 +76,7 @@ This report proves local benchmark reproducibility only. It keeps external provi
|
||||
| output_cases | `evals/output/cases.jsonl` | present | `a6ae96857116` |
|
||||
| output_schema | `evals/output/schema.json` | present | `8ee340c95064` |
|
||||
| output_scorecard | `reports/output_quality_scorecard.json` | present | `0806258a8e08` |
|
||||
| output_execution | `reports/output_execution_runs.json` | present | `9d1dbd75c98b` |
|
||||
| output_execution | `reports/output_execution_runs.json` | present | `db2564dbc622` |
|
||||
| blind_review | `reports/output_blind_review_pack.json` | present | `bbe2db8ec277` |
|
||||
| review_adjudication | `reports/output_review_adjudication.json` | present | `91fd88dd9b0f` |
|
||||
| trigger_scorecard | `reports/route_scorecard.json` | present | `c164e83e36d0` |
|
||||
|
||||
@@ -6,9 +6,9 @@
|
||||
"context_budget_tier": "production",
|
||||
"context_budget_limit": 1000,
|
||||
"skill_body_tokens": 797,
|
||||
"other_text_tokens": 1139278,
|
||||
"other_text_tokens": 1139267,
|
||||
"estimated_initial_load_tokens": 990,
|
||||
"estimated_total_text_tokens": 1140075,
|
||||
"estimated_total_text_tokens": 1140064,
|
||||
"deferred_resource_tokens": 515669,
|
||||
"deferred_resource_warn_threshold": 120000,
|
||||
"deferred_resource_dirs": [
|
||||
|
||||
+101
-103
@@ -306,8 +306,8 @@
|
||||
"key": "benchmark-release-lock-self-consistency",
|
||||
"label": "Benchmark release lock matches source dirty state",
|
||||
"status": "pass",
|
||||
"expected": false,
|
||||
"actual": false,
|
||||
"expected": true,
|
||||
"actual": true,
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json"
|
||||
],
|
||||
@@ -321,7 +321,7 @@
|
||||
"actual": {
|
||||
"available": true,
|
||||
"clean": false,
|
||||
"changed_file_count": 56
|
||||
"changed_file_count": 12
|
||||
},
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json"
|
||||
@@ -362,8 +362,8 @@
|
||||
"key": "overview-benchmark-commit",
|
||||
"label": "overview embeds the benchmark commit",
|
||||
"status": "pass",
|
||||
"expected": "7050664b482a8ed9ff8d763f08800902fdf1f02d",
|
||||
"actual": "7050664b482a8ed9ff8d763f08800902fdf1f02d",
|
||||
"expected": "cd71fd61e4d1c8db758ac0d2e9d1873a5a4ef547",
|
||||
"actual": "cd71fd61e4d1c8db758ac0d2e9d1873a5a4ef547",
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json",
|
||||
"reports/skill-overview.json"
|
||||
@@ -375,30 +375,30 @@
|
||||
"label": "overview embeds benchmark summary fields",
|
||||
"status": "pass",
|
||||
"expected": {
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"source_contract_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 19,
|
||||
"world_class_source_pass_count": 9,
|
||||
"world_class_source_blocked_count": 10,
|
||||
"world_class_source_pass_count": 10,
|
||||
"world_class_source_blocked_count": 9,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 5
|
||||
"public_claim_blocker_count": 4
|
||||
},
|
||||
"actual": {
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"source_contract_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 19,
|
||||
"world_class_source_pass_count": 9,
|
||||
"world_class_source_blocked_count": 10,
|
||||
"world_class_source_pass_count": 10,
|
||||
"world_class_source_blocked_count": 9,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 5
|
||||
"public_claim_blocker_count": 4
|
||||
},
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json",
|
||||
@@ -412,13 +412,13 @@
|
||||
"status": "pass",
|
||||
"expected": {
|
||||
"event_count": 1,
|
||||
"adoption_sample_count": 0,
|
||||
"activation_count": 0,
|
||||
"accepted_count": 0,
|
||||
"adoption_rate": 0,
|
||||
"adoption_sample_count": 1,
|
||||
"activation_count": 1,
|
||||
"accepted_count": 1,
|
||||
"adoption_rate": 100.0,
|
||||
"risk_band": "low",
|
||||
"event_types": {
|
||||
"review_event": 1
|
||||
"skill_activation": 1
|
||||
},
|
||||
"source_types": {
|
||||
"manual": 1
|
||||
@@ -426,13 +426,13 @@
|
||||
},
|
||||
"actual": {
|
||||
"event_count": 1,
|
||||
"adoption_sample_count": 0,
|
||||
"activation_count": 0,
|
||||
"accepted_count": 0,
|
||||
"adoption_rate": 0,
|
||||
"adoption_sample_count": 1,
|
||||
"activation_count": 1,
|
||||
"accepted_count": 1,
|
||||
"adoption_rate": 100.0,
|
||||
"risk_band": "low",
|
||||
"event_types": {
|
||||
"review_event": 1
|
||||
"skill_activation": 1
|
||||
},
|
||||
"source_types": {
|
||||
"manual": 1
|
||||
@@ -455,8 +455,8 @@
|
||||
"human_pending_count": 1,
|
||||
"external_pending_count": 3,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 9,
|
||||
"source_blocked_count": 10,
|
||||
"source_pass_count": 10,
|
||||
"source_blocked_count": 9,
|
||||
"ready_to_claim_world_class": false,
|
||||
"decision": "evidence-pending"
|
||||
},
|
||||
@@ -467,8 +467,8 @@
|
||||
"human_pending_count": 1,
|
||||
"external_pending_count": 3,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 9,
|
||||
"source_blocked_count": 10,
|
||||
"source_pass_count": 10,
|
||||
"source_blocked_count": 9,
|
||||
"ready_to_claim_world_class": false,
|
||||
"decision": "evidence-pending"
|
||||
},
|
||||
@@ -488,7 +488,7 @@
|
||||
"pending_count": 4,
|
||||
"accepted_count": 0,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 9
|
||||
"source_pass_count": 10
|
||||
},
|
||||
"actual": {
|
||||
"ready": false,
|
||||
@@ -496,7 +496,7 @@
|
||||
"pending_count": 4,
|
||||
"accepted_count": 0,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 9
|
||||
"source_pass_count": 10
|
||||
},
|
||||
"paths": [
|
||||
"reports/world_class_evidence_ledger.json",
|
||||
@@ -508,8 +508,8 @@
|
||||
"key": "interpretation-benchmark-commit",
|
||||
"label": "interpretation embeds the benchmark commit",
|
||||
"status": "pass",
|
||||
"expected": "7050664b482a8ed9ff8d763f08800902fdf1f02d",
|
||||
"actual": "7050664b482a8ed9ff8d763f08800902fdf1f02d",
|
||||
"expected": "cd71fd61e4d1c8db758ac0d2e9d1873a5a4ef547",
|
||||
"actual": "cd71fd61e4d1c8db758ac0d2e9d1873a5a4ef547",
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json",
|
||||
"reports/skill-interpretation.json"
|
||||
@@ -521,30 +521,30 @@
|
||||
"label": "interpretation embeds benchmark summary fields",
|
||||
"status": "pass",
|
||||
"expected": {
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"source_contract_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 19,
|
||||
"world_class_source_pass_count": 9,
|
||||
"world_class_source_blocked_count": 10,
|
||||
"world_class_source_pass_count": 10,
|
||||
"world_class_source_blocked_count": 9,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 5
|
||||
"public_claim_blocker_count": 4
|
||||
},
|
||||
"actual": {
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"source_contract_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 19,
|
||||
"world_class_source_pass_count": 9,
|
||||
"world_class_source_blocked_count": 10,
|
||||
"world_class_source_pass_count": 10,
|
||||
"world_class_source_blocked_count": 9,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 5
|
||||
"public_claim_blocker_count": 4
|
||||
},
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json",
|
||||
@@ -558,13 +558,13 @@
|
||||
"status": "pass",
|
||||
"expected": {
|
||||
"event_count": 1,
|
||||
"adoption_sample_count": 0,
|
||||
"activation_count": 0,
|
||||
"accepted_count": 0,
|
||||
"adoption_rate": 0,
|
||||
"adoption_sample_count": 1,
|
||||
"activation_count": 1,
|
||||
"accepted_count": 1,
|
||||
"adoption_rate": 100.0,
|
||||
"risk_band": "low",
|
||||
"event_types": {
|
||||
"review_event": 1
|
||||
"skill_activation": 1
|
||||
},
|
||||
"source_types": {
|
||||
"manual": 1
|
||||
@@ -572,13 +572,13 @@
|
||||
},
|
||||
"actual": {
|
||||
"event_count": 1,
|
||||
"adoption_sample_count": 0,
|
||||
"activation_count": 0,
|
||||
"accepted_count": 0,
|
||||
"adoption_rate": 0,
|
||||
"adoption_sample_count": 1,
|
||||
"activation_count": 1,
|
||||
"accepted_count": 1,
|
||||
"adoption_rate": 100.0,
|
||||
"risk_band": "low",
|
||||
"event_types": {
|
||||
"review_event": 1
|
||||
"skill_activation": 1
|
||||
},
|
||||
"source_types": {
|
||||
"manual": 1
|
||||
@@ -601,8 +601,8 @@
|
||||
"human_pending_count": 1,
|
||||
"external_pending_count": 3,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 9,
|
||||
"source_blocked_count": 10,
|
||||
"source_pass_count": 10,
|
||||
"source_blocked_count": 9,
|
||||
"ready_to_claim_world_class": false,
|
||||
"decision": "evidence-pending"
|
||||
},
|
||||
@@ -613,8 +613,8 @@
|
||||
"human_pending_count": 1,
|
||||
"external_pending_count": 3,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 9,
|
||||
"source_blocked_count": 10,
|
||||
"source_pass_count": 10,
|
||||
"source_blocked_count": 9,
|
||||
"ready_to_claim_world_class": false,
|
||||
"decision": "evidence-pending"
|
||||
},
|
||||
@@ -634,7 +634,7 @@
|
||||
"pending_count": 4,
|
||||
"accepted_count": 0,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 9
|
||||
"source_pass_count": 10
|
||||
},
|
||||
"actual": {
|
||||
"ready": false,
|
||||
@@ -642,7 +642,7 @@
|
||||
"pending_count": 4,
|
||||
"accepted_count": 0,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 9
|
||||
"source_pass_count": 10
|
||||
},
|
||||
"paths": [
|
||||
"reports/world_class_evidence_ledger.json",
|
||||
@@ -1441,7 +1441,7 @@
|
||||
"external_pending_count": 3,
|
||||
"human_pending_count": 1,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 9,
|
||||
"source_pass_count": 10,
|
||||
"conclusion_zh": "世界级证据尚未完成:4 项待补,0 项已接受。",
|
||||
"conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.",
|
||||
"entries": [
|
||||
@@ -1501,8 +1501,7 @@
|
||||
"summary_zh": "真实外部客户端 metadata-only 事件仍未导入。",
|
||||
"summary_en": "Real external-client metadata-only events have not been imported yet.",
|
||||
"blocked_checks": [
|
||||
"External events",
|
||||
"Adoption sample"
|
||||
"External events"
|
||||
]
|
||||
}
|
||||
]
|
||||
@@ -1516,7 +1515,7 @@
|
||||
"external_pending_count": 3,
|
||||
"human_pending_count": 1,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 9,
|
||||
"source_pass_count": 10,
|
||||
"conclusion_zh": "世界级证据尚未完成:4 项待补,0 项已接受。",
|
||||
"conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.",
|
||||
"entries": [
|
||||
@@ -1576,8 +1575,7 @@
|
||||
"summary_zh": "真实外部客户端 metadata-only 事件仍未导入。",
|
||||
"summary_en": "Real external-client metadata-only events have not been imported yet.",
|
||||
"blocked_checks": [
|
||||
"External events",
|
||||
"Adoption sample"
|
||||
"External events"
|
||||
]
|
||||
}
|
||||
]
|
||||
@@ -1927,15 +1925,15 @@
|
||||
"expected": {
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 19,
|
||||
"world_class_source_pass_count": 9,
|
||||
"world_class_source_blocked_count": 10,
|
||||
"world_class_source_pass_count": 10,
|
||||
"world_class_source_blocked_count": 9,
|
||||
"public_claim_ready": false
|
||||
},
|
||||
"actual": {
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 19,
|
||||
"world_class_source_pass_count": 9,
|
||||
"world_class_source_blocked_count": 10,
|
||||
"world_class_source_pass_count": 10,
|
||||
"world_class_source_blocked_count": 9,
|
||||
"public_claim_ready": false
|
||||
},
|
||||
"paths": [
|
||||
@@ -1951,8 +1949,8 @@
|
||||
"expected": {
|
||||
"pending_count": 4,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 9,
|
||||
"source_blocked_count": 10,
|
||||
"source_pass_count": 10,
|
||||
"source_blocked_count": 9,
|
||||
"ready_to_claim_world_class": false,
|
||||
"preflight_counts_as_evidence": false,
|
||||
"credential_value_exposed": false
|
||||
@@ -1960,8 +1958,8 @@
|
||||
"actual": {
|
||||
"pending_count": 4,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 9,
|
||||
"source_blocked_count": 10,
|
||||
"source_pass_count": 10,
|
||||
"source_blocked_count": 9,
|
||||
"ready_to_claim_world_class": false,
|
||||
"preflight_counts_as_evidence": false,
|
||||
"credential_value_exposed": false
|
||||
@@ -2138,7 +2136,7 @@
|
||||
"summary": {
|
||||
"phase_queue_count": 2,
|
||||
"phase_queue_blocked_count": 2,
|
||||
"phase_queue_row_count": 14,
|
||||
"phase_queue_row_count": 13,
|
||||
"phase_queue_next_phase": "unblock-access",
|
||||
"phase_queue_next_action_id": "human-adjudication-precheck-human-reviewer",
|
||||
"phase_queue_next_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
|
||||
@@ -2171,8 +2169,8 @@
|
||||
"phase": "collect-source",
|
||||
"priority": 40,
|
||||
"status": "blocked",
|
||||
"blocked_count": 10,
|
||||
"row_count": 10,
|
||||
"blocked_count": 9,
|
||||
"row_count": 9,
|
||||
"owners": [
|
||||
"Browser/Chrome/IDE/provider client integrator",
|
||||
"human reviewer",
|
||||
@@ -2314,15 +2312,15 @@
|
||||
"phase": "collect-source",
|
||||
"priority": 40,
|
||||
"status": "blocked",
|
||||
"blocked_count": 2,
|
||||
"row_count": 2,
|
||||
"blocked_count": 1,
|
||||
"row_count": 1,
|
||||
"owners": [
|
||||
"Browser/Chrome/IDE/provider client integrator"
|
||||
],
|
||||
"evidence_keys": [
|
||||
"native-client-telemetry"
|
||||
],
|
||||
"next_action_id": "native-client-telemetry-source-check-adoption_sample_count",
|
||||
"next_action_id": "native-client-telemetry-source-check-external_source_events",
|
||||
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
|
||||
"counts_as_completion": false
|
||||
}
|
||||
@@ -2332,7 +2330,7 @@
|
||||
"operator_runbook_summary": {
|
||||
"phase_queue_count": 2,
|
||||
"phase_queue_blocked_count": 2,
|
||||
"phase_queue_row_count": 14,
|
||||
"phase_queue_row_count": 13,
|
||||
"phase_queue_next_phase": "unblock-access",
|
||||
"phase_queue_next_action_id": "human-adjudication-precheck-human-reviewer",
|
||||
"phase_queue_next_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
|
||||
@@ -2365,8 +2363,8 @@
|
||||
"phase": "collect-source",
|
||||
"priority": 40,
|
||||
"status": "blocked",
|
||||
"blocked_count": 10,
|
||||
"row_count": 10,
|
||||
"blocked_count": 9,
|
||||
"row_count": 9,
|
||||
"owners": [
|
||||
"Browser/Chrome/IDE/provider client integrator",
|
||||
"human reviewer",
|
||||
@@ -2508,15 +2506,15 @@
|
||||
"phase": "collect-source",
|
||||
"priority": 40,
|
||||
"status": "blocked",
|
||||
"blocked_count": 2,
|
||||
"row_count": 2,
|
||||
"blocked_count": 1,
|
||||
"row_count": 1,
|
||||
"owners": [
|
||||
"Browser/Chrome/IDE/provider client integrator"
|
||||
],
|
||||
"evidence_keys": [
|
||||
"native-client-telemetry"
|
||||
],
|
||||
"next_action_id": "native-client-telemetry-source-check-adoption_sample_count",
|
||||
"next_action_id": "native-client-telemetry-source-check-external_source_events",
|
||||
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
|
||||
"counts_as_completion": false
|
||||
}
|
||||
@@ -2646,15 +2644,15 @@
|
||||
"phase": "collect-source",
|
||||
"priority": 40,
|
||||
"status": "blocked",
|
||||
"blocked_count": 2,
|
||||
"row_count": 2,
|
||||
"blocked_count": 1,
|
||||
"row_count": 1,
|
||||
"owners": [
|
||||
"Browser/Chrome/IDE/provider client integrator"
|
||||
],
|
||||
"evidence_keys": [
|
||||
"native-client-telemetry"
|
||||
],
|
||||
"next_action_id": "native-client-telemetry-source-check-adoption_sample_count",
|
||||
"next_action_id": "native-client-telemetry-source-check-external_source_events",
|
||||
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
|
||||
"counts_as_completion": false
|
||||
}
|
||||
@@ -2665,7 +2663,7 @@
|
||||
"summary": {
|
||||
"phase_queue_count": 2,
|
||||
"phase_queue_blocked_count": 2,
|
||||
"phase_queue_row_count": 14,
|
||||
"phase_queue_row_count": 13,
|
||||
"phase_queue_next_phase": "unblock-access",
|
||||
"phase_queue_next_action_id": "human-adjudication-precheck-human-reviewer",
|
||||
"phase_queue_next_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
|
||||
@@ -2698,8 +2696,8 @@
|
||||
"phase": "collect-source",
|
||||
"priority": 40,
|
||||
"status": "blocked",
|
||||
"blocked_count": 10,
|
||||
"row_count": 10,
|
||||
"blocked_count": 9,
|
||||
"row_count": 9,
|
||||
"owners": [
|
||||
"Browser/Chrome/IDE/provider client integrator",
|
||||
"human reviewer",
|
||||
@@ -2720,7 +2718,7 @@
|
||||
"operator_runbook_summary": {
|
||||
"phase_queue_count": 2,
|
||||
"phase_queue_blocked_count": 2,
|
||||
"phase_queue_row_count": 14,
|
||||
"phase_queue_row_count": 13,
|
||||
"phase_queue_next_phase": "unblock-access",
|
||||
"phase_queue_next_action_id": "human-adjudication-precheck-human-reviewer",
|
||||
"phase_queue_next_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
|
||||
@@ -2753,8 +2751,8 @@
|
||||
"phase": "collect-source",
|
||||
"priority": 40,
|
||||
"status": "blocked",
|
||||
"blocked_count": 10,
|
||||
"row_count": 10,
|
||||
"blocked_count": 9,
|
||||
"row_count": 9,
|
||||
"owners": [
|
||||
"Browser/Chrome/IDE/provider client integrator",
|
||||
"human reviewer",
|
||||
@@ -2896,15 +2894,15 @@
|
||||
"phase": "collect-source",
|
||||
"priority": 40,
|
||||
"status": "blocked",
|
||||
"blocked_count": 2,
|
||||
"row_count": 2,
|
||||
"blocked_count": 1,
|
||||
"row_count": 1,
|
||||
"owners": [
|
||||
"Browser/Chrome/IDE/provider client integrator"
|
||||
],
|
||||
"evidence_keys": [
|
||||
"native-client-telemetry"
|
||||
],
|
||||
"next_action_id": "native-client-telemetry-source-check-adoption_sample_count",
|
||||
"next_action_id": "native-client-telemetry-source-check-external_source_events",
|
||||
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
|
||||
"counts_as_completion": false
|
||||
}
|
||||
@@ -3034,15 +3032,15 @@
|
||||
"phase": "collect-source",
|
||||
"priority": 40,
|
||||
"status": "blocked",
|
||||
"blocked_count": 2,
|
||||
"row_count": 2,
|
||||
"blocked_count": 1,
|
||||
"row_count": 1,
|
||||
"owners": [
|
||||
"Browser/Chrome/IDE/provider client integrator"
|
||||
],
|
||||
"evidence_keys": [
|
||||
"native-client-telemetry"
|
||||
],
|
||||
"next_action_id": "native-client-telemetry-source-check-adoption_sample_count",
|
||||
"next_action_id": "native-client-telemetry-source-check-external_source_events",
|
||||
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
|
||||
"counts_as_completion": false
|
||||
}
|
||||
@@ -3172,15 +3170,15 @@
|
||||
"phase": "collect-source",
|
||||
"priority": 40,
|
||||
"status": "blocked",
|
||||
"blocked_count": 2,
|
||||
"row_count": 2,
|
||||
"blocked_count": 1,
|
||||
"row_count": 1,
|
||||
"owners": [
|
||||
"Browser/Chrome/IDE/provider client integrator"
|
||||
],
|
||||
"evidence_keys": [
|
||||
"native-client-telemetry"
|
||||
],
|
||||
"next_action_id": "native-client-telemetry-source-check-adoption_sample_count",
|
||||
"next_action_id": "native-client-telemetry-source-check-external_source_events",
|
||||
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
|
||||
"counts_as_completion": false
|
||||
}
|
||||
@@ -3280,8 +3278,8 @@
|
||||
"human_pending_count": 1,
|
||||
"external_pending_count": 3,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 9,
|
||||
"source_blocked_count": 10,
|
||||
"source_pass_count": 10,
|
||||
"source_blocked_count": 9,
|
||||
"plan_keys": [
|
||||
"human-adjudication",
|
||||
"native-client-telemetry",
|
||||
@@ -3429,8 +3427,8 @@
|
||||
"human_pending_count": 1,
|
||||
"external_pending_count": 3,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 9,
|
||||
"source_blocked_count": 10,
|
||||
"source_pass_count": 10,
|
||||
"source_blocked_count": 9,
|
||||
"plan_keys": [
|
||||
"human-adjudication",
|
||||
"native-client-telemetry",
|
||||
|
||||
@@ -34,7 +34,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 32.49,
|
||||
"duration_ms": 33.77,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -62,7 +62,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 28.38,
|
||||
"duration_ms": 31.71,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -85,7 +85,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 28.39,
|
||||
"duration_ms": 29.59,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -113,7 +113,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 28.18,
|
||||
"duration_ms": 29.77,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -136,7 +136,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 28.12,
|
||||
"duration_ms": 32.5,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -164,7 +164,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 28.24,
|
||||
"duration_ms": 30.06,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -187,7 +187,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 29.02,
|
||||
"duration_ms": 35.9,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -214,7 +214,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 30.75,
|
||||
"duration_ms": 29.67,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -237,7 +237,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 35.6,
|
||||
"duration_ms": 30.52,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -266,7 +266,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 31.44,
|
||||
"duration_ms": 30.91,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
|
||||
@@ -23,16 +23,16 @@ Command runner evidence is present. This proves the eval harness executed an ext
|
||||
|
||||
| Case | Variant | Mode | Model | Duration ms | Tokens | Score | Status |
|
||||
| --- | --- | --- | --- | ---: | ---: | ---: | --- |
|
||||
| skill-package-contract | baseline | command | local-output-eval-runner | 32.49 | 33 | 0.0 | pass |
|
||||
| skill-package-contract | with_skill | command | local-output-eval-runner | 28.38 | 73 | 100.0 | pass |
|
||||
| output-eval-expectation | baseline | command | local-output-eval-runner | 28.39 | 36 | 0.0 | pass |
|
||||
| output-eval-expectation | with_skill | command | local-output-eval-runner | 28.18 | 80 | 100.0 | pass |
|
||||
| ir-before-packaging | baseline | command | local-output-eval-runner | 28.12 | 33 | 0.0 | pass |
|
||||
| ir-before-packaging | with_skill | command | local-output-eval-runner | 28.24 | 80 | 100.0 | pass |
|
||||
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 29.02 | 36 | 0.0 | pass |
|
||||
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 30.75 | 65 | 100.0 | pass |
|
||||
| file-backed-governed-package | baseline | command | local-output-eval-runner | 35.6 | 37 | 0.0 | pass |
|
||||
| file-backed-governed-package | with_skill | command | local-output-eval-runner | 31.44 | 98 | 100.0 | pass |
|
||||
| skill-package-contract | baseline | command | local-output-eval-runner | 33.77 | 33 | 0.0 | pass |
|
||||
| skill-package-contract | with_skill | command | local-output-eval-runner | 31.71 | 73 | 100.0 | pass |
|
||||
| output-eval-expectation | baseline | command | local-output-eval-runner | 29.59 | 36 | 0.0 | pass |
|
||||
| output-eval-expectation | with_skill | command | local-output-eval-runner | 29.77 | 80 | 100.0 | pass |
|
||||
| ir-before-packaging | baseline | command | local-output-eval-runner | 32.5 | 33 | 0.0 | pass |
|
||||
| ir-before-packaging | with_skill | command | local-output-eval-runner | 30.06 | 80 | 100.0 | pass |
|
||||
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 35.9 | 36 | 0.0 | pass |
|
||||
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 29.67 | 65 | 100.0 | pass |
|
||||
| file-backed-governed-package | baseline | command | local-output-eval-runner | 30.52 | 37 | 0.0 | pass |
|
||||
| file-backed-governed-package | with_skill | command | local-output-eval-runner | 30.91 | 98 | 100.0 | pass |
|
||||
|
||||
## Next Fixes
|
||||
|
||||
|
||||
@@ -772,12 +772,12 @@
|
||||
|
||||
<section>
|
||||
<h2>核心指标</h2>
|
||||
<div class="metrics"><article class='metric'><span>Skill IR</span><strong>2.0.0</strong><p>5 targets in platform-neutral contract</p></article><article class='metric'><span>Compiler</span><strong>5/5</strong><p>target contracts compiled from Skill IR</p></article><article class='metric'><span>Output Delta</span><strong>100.0</strong><p>5 cases; 1 file-backed</p></article><article class='metric'><span>Exec Runs</span><strong>10</strong><p>command 10; model 0; recorded 0</p></article><article class='metric'><span>Blind A/B</span><strong>5</strong><p>review pairs hide baseline vs with-skill labels</p></article><article class='metric'><span>Review Kit</span><strong>0/5</strong><p>pending 5; answer key hidden</p></article><article class='metric'><span>Review A/B</span><strong>0/5</strong><p>adjudication decisions; pending 5</p></article><article class='metric'><span>Public Claim</span><strong>blocked</strong><p>5 blockers; local reproducible true</p></article><article class='metric'><span>Blueprint</span><strong>21/21</strong><p>2.0 coverage; extensions partial 0, planned 0; evidence pending 4</p></article><article class='metric'><span>Runtime</span><strong>5/5</strong><p>target conformance pass rate</p></article><article class='metric'><span>Perm Probe</span><strong>4/4</strong><p>0 native; 4 installer-enforced</p></article><article class='metric'><span>Trust</span><strong>0</strong><p>152 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>231 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>696 largest lines; 0 watchlist; 4 early; 68 CLI handlers; 18 in entrypoint</p></article><article class='metric'><span>Atlas</span><strong>5</strong><p>12 scanned skills; route collisions</p></article><article class='metric'><span>Drift</span><strong>low</strong><p>1 metadata events; 0 missed triggers</p></article><article class='metric'><span>Daily Ops</span><strong>5</strong><p>proposal-review; approval 0; release lock true</p></article><article class='metric'><span>Weekly Queue</span><strong>5</strong><p>curator-review; ready 1; top score 88</p></article><article class='metric'><span>Waivers</span><strong>0</strong><p>0 gates covered; human risk decisions</p></article><article class='metric'><span>Intake</span><strong>4/4</strong><p>0 valid submissions; 0 invalid</p></article><article class='metric'><span>Claim Guard</span><strong>0</strong><p>182 public surfaces scanned</p></article><article class='metric'><span>Notes</span><strong>0/0</strong><p>0 open blocker annotations</p></article><article class='metric'><span>Registry</span><strong>1.1.0</strong><p>5 targets; MIT license</p></article><article class='metric'><span>Archive</span><strong>pass</strong><p>689 zip entries; package verification</p></article><article class='metric'><span>Install</span><strong>pass</strong><p>4 adapters; 12 permissions enforced; 0 permission failures</p></article><article class='metric'><span>Upgrade</span><strong>minor</strong><p>declared minor; 0 breaking changes</p></article></div>
|
||||
<div class="metrics"><article class='metric'><span>Skill IR</span><strong>2.0.0</strong><p>5 targets in platform-neutral contract</p></article><article class='metric'><span>Compiler</span><strong>5/5</strong><p>target contracts compiled from Skill IR</p></article><article class='metric'><span>Output Delta</span><strong>100.0</strong><p>5 cases; 1 file-backed</p></article><article class='metric'><span>Exec Runs</span><strong>10</strong><p>command 10; model 0; recorded 0</p></article><article class='metric'><span>Blind A/B</span><strong>5</strong><p>review pairs hide baseline vs with-skill labels</p></article><article class='metric'><span>Review Kit</span><strong>0/5</strong><p>pending 5; answer key hidden</p></article><article class='metric'><span>Review A/B</span><strong>0/5</strong><p>adjudication decisions; pending 5</p></article><article class='metric'><span>Public Claim</span><strong>blocked</strong><p>4 blockers; local reproducible true</p></article><article class='metric'><span>Blueprint</span><strong>21/21</strong><p>2.0 coverage; extensions partial 0, planned 0; evidence pending 4</p></article><article class='metric'><span>Runtime</span><strong>5/5</strong><p>target conformance pass rate</p></article><article class='metric'><span>Perm Probe</span><strong>4/4</strong><p>0 native; 4 installer-enforced</p></article><article class='metric'><span>Trust</span><strong>0</strong><p>152 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>231 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>696 largest lines; 0 watchlist; 4 early; 68 CLI handlers; 18 in entrypoint</p></article><article class='metric'><span>Atlas</span><strong>5</strong><p>12 scanned skills; route collisions</p></article><article class='metric'><span>Drift</span><strong>low</strong><p>1 metadata events; 0 missed triggers</p></article><article class='metric'><span>Daily Ops</span><strong>5</strong><p>proposal-review; approval 0; release lock true</p></article><article class='metric'><span>Weekly Queue</span><strong>5</strong><p>curator-review; ready 1; top score 88</p></article><article class='metric'><span>Waivers</span><strong>0</strong><p>0 gates covered; human risk decisions</p></article><article class='metric'><span>Intake</span><strong>4/4</strong><p>0 valid submissions; 0 invalid</p></article><article class='metric'><span>Claim Guard</span><strong>0</strong><p>182 public surfaces scanned</p></article><article class='metric'><span>Notes</span><strong>0/0</strong><p>0 open blocker annotations</p></article><article class='metric'><span>Registry</span><strong>1.1.0</strong><p>5 targets; MIT license</p></article><article class='metric'><span>Archive</span><strong>pass</strong><p>689 zip entries; package verification</p></article><article class='metric'><span>Install</span><strong>pass</strong><p>4 adapters; 12 permissions enforced; 0 permission failures</p></article><article class='metric'><span>Upgrade</span><strong>minor</strong><p>declared minor; 0 breaking changes</p></article></div>
|
||||
</section>
|
||||
|
||||
<section>
|
||||
<h2>审查闸门</h2>
|
||||
<div class="gates"><article class='gate pass'><div><span>通过</span><h3>意图画布</h3></div><p>intent confidence 100/100; Intent is clear enough to package the first routeable version.</p><footer>reports/intent-confidence.json <a href='intent-confidence.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>触发实验</h3></div><p>13 trigger cases; 0 misroutes; 0 ambiguous</p><footer>reports/route_scorecard.json <a href='route_scorecard.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>输出实验</h3></div><p>5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5; review pending 5</p><footer>reports/output_quality_scorecard.json <a href='output_quality_scorecard.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>上下文</h3></div><p>initial load 990/1000; deferred 515669/120000; top deferred scripts 454366; resource governance governed; quality density 131.3</p><footer>reports/context_budget.json <a href='context_budget.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运行矩阵</h3></div><p>5 / 5 targets pass</p><footer>reports/conformance_matrix.json <a href='conformance_matrix.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>信任报告</h3></div><p>0 secrets; 152 scripts; 3 network-capable scripts; 0 help smoke failures</p><footer>reports/security_trust_report.json <a href='security_trust_report.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>Python 兼容</h3></div><p>Python 3.11; 231 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards</p><footer>reports/python_compatibility.json <a href='python_compatibility.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>架构维护</h3></div><p>228 Python files; 0 hotspots; 0 watchlist files; 4 early watch files; 0 blockers; largest 696 lines; 68 CLI handlers; 18 in entrypoint</p><footer>reports/architecture_maintainability.json <a href='architecture_maintainability.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限批准</h3></div><p>3/3 permissions approved; gaps 0; required file_write, network, subprocess</p><footer>reports/security_trust_report.json + security/permission_policy.json <a href='../security/permission_policy.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限探针</h3></div><p>4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4</p><footer>reports/runtime_permission_probes.json <a href='runtime_permission_probes.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>组合治理</h3></div><p>12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues</p><footer>reports/skill_atlas.json <a href='skill_atlas.html'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运营回路</h3></div><p>1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false</p><footer>reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly <a href='adoption_drift_report.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>人工批准</h3></div><p>0 active waivers; 1 warning gates still need reviewer decision</p><footer>reports/review_waivers.json <a href='review_waivers.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>世界证据</h3></div><p>4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 10/19 pass; 9 blocked; overclaim guard true</p><footer>reports/world_class_evidence_ledger.json <a href='world_class_evidence_ledger.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>注册审计</h3></div><p>yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures</p><footer>reports/registry_audit.json + reports/install_simulation.json <a href='registry_audit.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>发布路线</h3></div><p>0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended</p><footer>reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md <a href='promotion_decisions.md'>证据</a></footer></article></div>
|
||||
<div class="gates"><article class='gate pass'><div><span>通过</span><h3>意图画布</h3></div><p>intent confidence 100/100; Intent is clear enough to package the first routeable version.</p><footer>reports/intent-confidence.json <a href='intent-confidence.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>触发实验</h3></div><p>13 trigger cases; 0 misroutes; 0 ambiguous</p><footer>reports/route_scorecard.json <a href='route_scorecard.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>输出实验</h3></div><p>5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5; review pending 5</p><footer>reports/output_quality_scorecard.json <a href='output_quality_scorecard.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>上下文</h3></div><p>initial load 990/1000; deferred 515669/120000; top deferred scripts 454366; resource governance governed; quality density 131.3</p><footer>reports/context_budget.json <a href='context_budget.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运行矩阵</h3></div><p>5 / 5 targets pass</p><footer>reports/conformance_matrix.json <a href='conformance_matrix.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>信任报告</h3></div><p>0 secrets; 152 scripts; 3 network-capable scripts; 0 help smoke failures</p><footer>reports/security_trust_report.json <a href='security_trust_report.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>Python 兼容</h3></div><p>Python 3.11; 231 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards</p><footer>reports/python_compatibility.json <a href='python_compatibility.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>架构维护</h3></div><p>228 Python files; 0 hotspots; 0 watchlist files; 4 early watch files; 0 blockers; largest 696 lines; 68 CLI handlers; 18 in entrypoint</p><footer>reports/architecture_maintainability.json <a href='architecture_maintainability.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限批准</h3></div><p>3/3 permissions approved; gaps 0; required file_write, network, subprocess</p><footer>reports/security_trust_report.json + security/permission_policy.json <a href='../security/permission_policy.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限探针</h3></div><p>4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4</p><footer>reports/runtime_permission_probes.json <a href='runtime_permission_probes.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>组合治理</h3></div><p>12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues</p><footer>reports/skill_atlas.json <a href='skill_atlas.html'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运营回路</h3></div><p>1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true</p><footer>reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly <a href='adoption_drift_report.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>人工批准</h3></div><p>0 active waivers; 1 warning gates still need reviewer decision</p><footer>reports/review_waivers.json <a href='review_waivers.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>世界证据</h3></div><p>4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 10/19 pass; 9 blocked; overclaim guard true</p><footer>reports/world_class_evidence_ledger.json <a href='world_class_evidence_ledger.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>注册审计</h3></div><p>yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures</p><footer>reports/registry_audit.json + reports/install_simulation.json <a href='registry_audit.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>发布路线</h3></div><p>0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended</p><footer>reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md <a href='promotion_decisions.md'>证据</a></footer></article></div>
|
||||
</section>
|
||||
|
||||
<section>
|
||||
@@ -874,14 +874,14 @@
|
||||
</section>
|
||||
|
||||
<section id="telemetry" class="twocol">
|
||||
<div class="panel"><h2>运营回路</h2><p>1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false</p></div>
|
||||
<div class="panel"><h2>运营回路</h2><p>1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true</p></div>
|
||||
<div class="panel"><h2>漂移信号</h2><dl class='kv-grid'><div><dt>事件数</dt><dd>1</dd></div><div><dt>采用率</dt><dd>100</dd></div><div><dt>漏触发</dt><dd>0</dd></div><div><dt>Bad Output Count</dt><dd>0</dd></div><div><dt>风险带</dt><dd>low</dd></div></dl></div>
|
||||
</section>
|
||||
|
||||
|
||||
<section class="twocol">
|
||||
<div class="panel"><h2>日常运维</h2><dl class='kv-grid'><div><dt>决策</dt><dd>proposal-review</dd></div><div><dt>提案数</dt><dd>5</dd></div><div><dt>Approval Count</dt><dd>0</dd></div><div><dt>Pending Review Count</dt><dd>0</dd></div><div><dt>发布锁</dt><dd>是</dd></div><div><dt>世界级</dt><dd>否</dd></div><div><dt>Writes Source Files</dt><dd>否</dd></div><div><dt>Auto Patch Enabled</dt><dd>否</dd></div></dl></div>
|
||||
<div class="panel"><h2>周度队列</h2><dl class='kv-grid'><div><dt>决策</dt><dd>curator-review</dd></div><div><dt>Week Id</dt><dd>2026-W25</dd></div><div><dt>日报数</dt><dd>2</dd></div><div><dt>唯一机会</dt><dd>5</dd></div><div><dt>待批准复核</dt><dd>1</dd></div><div><dt>提案复核</dt><dd>4</dd></div><div><dt>Top Score</dt><dd>88</dd></div><div><dt>发布锁</dt><dd>否</dd></div><div><dt>Writes Source Files</dt><dd>否</dd></div><div><dt>Auto Patch Enabled</dt><dd>否</dd></div></dl></div>
|
||||
<div class="panel"><h2>周度队列</h2><dl class='kv-grid'><div><dt>决策</dt><dd>curator-review</dd></div><div><dt>Week Id</dt><dd>2026-W25</dd></div><div><dt>日报数</dt><dd>2</dd></div><div><dt>唯一机会</dt><dd>5</dd></div><div><dt>待批准复核</dt><dd>1</dd></div><div><dt>提案复核</dt><dd>4</dd></div><div><dt>Top Score</dt><dd>88</dd></div><div><dt>发布锁</dt><dd>是</dd></div><div><dt>Writes Source Files</dt><dd>否</dd></div><div><dt>Auto Patch Enabled</dt><dd>否</dd></div></dl></div>
|
||||
</section>
|
||||
|
||||
|
||||
@@ -914,8 +914,8 @@
|
||||
</section>
|
||||
|
||||
<section class="twocol">
|
||||
<div class="panel"><h2>公开声明</h2><dl class='kv-grid'><div><dt>本地复现</dt><dd>是</dd></div><div><dt>发布锁</dt><dd>否</dd></div><div><dt>可公开声明</dt><dd>否</dd></div><div><dt>声明阻断</dt><dd>5</dd></div><div><dt>Provider 证据</dt><dd>否</dd></div><div><dt>人审完成</dt><dd>否</dd></div><div><dt>世界级就绪</dt><dd>否</dd></div></dl></div>
|
||||
<div class="panel"><h2>声明阻断</h2><ul class='issues'><li><strong>阻断</strong><span>release lock is not clean or commit is unavailable</span></li><li><strong>阻断</strong><span>provider-backed model holdout evidence is incomplete</span></li><li><strong>阻断</strong><span>human blind-review adjudication is incomplete</span></li><li><strong>阻断</strong><span>world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)</span></li><li><strong>阻断</strong><span>world-class source checks are not all accepted (10/19 pass, 9 blocked)</span></li></ul></div>
|
||||
<div class="panel"><h2>公开声明</h2><dl class='kv-grid'><div><dt>本地复现</dt><dd>是</dd></div><div><dt>发布锁</dt><dd>是</dd></div><div><dt>可公开声明</dt><dd>否</dd></div><div><dt>声明阻断</dt><dd>4</dd></div><div><dt>Provider 证据</dt><dd>否</dd></div><div><dt>人审完成</dt><dd>否</dd></div><div><dt>世界级就绪</dt><dd>否</dd></div></dl></div>
|
||||
<div class="panel"><h2>声明阻断</h2><ul class='issues'><li><strong>阻断</strong><span>provider-backed model holdout evidence is incomplete</span></li><li><strong>阻断</strong><span>human blind-review adjudication is incomplete</span></li><li><strong>阻断</strong><span>world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)</span></li><li><strong>阻断</strong><span>world-class source checks are not all accepted (10/19 pass, 9 blocked)</span></li></ul></div>
|
||||
</section>
|
||||
|
||||
<section class="twocol">
|
||||
|
||||
+61
-68
@@ -152,7 +152,7 @@
|
||||
"key": "operations-loop",
|
||||
"label": "运营回路",
|
||||
"status": "pass",
|
||||
"detail": "1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false",
|
||||
"detail": "1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true",
|
||||
"evidence": "reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly",
|
||||
"link": "adoption_drift_report.md",
|
||||
"review_action_id": "",
|
||||
@@ -2442,11 +2442,11 @@
|
||||
"ok": true,
|
||||
"summary": {
|
||||
"reproducibility_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"methodology_complete": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"evidence_bundle_sha256": "c31e8bd9e49e60f14344e25ae71dabf911612d9c1ae6aee292ce566c66b88fce",
|
||||
"evidence_bundle_sha256": "b29129730b143a8ee3e8f3976ea953ed7173e0c7de9c4e8a2fc2f4c47635fe15",
|
||||
"source_contract_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
|
||||
"output_case_count": 5,
|
||||
@@ -2466,15 +2466,15 @@
|
||||
"world_class_source_pass_count": 10,
|
||||
"world_class_source_blocked_count": 9,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 5,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 39,
|
||||
"source_tree_dirty": true,
|
||||
"source_changed_file_count": 5,
|
||||
"changed_file_count": 15,
|
||||
"source_tree_dirty": false,
|
||||
"source_changed_file_count": 0,
|
||||
"generated_tree_dirty": true,
|
||||
"generated_changed_file_count": 34
|
||||
"generated_changed_file_count": 15
|
||||
},
|
||||
"commit": "7050664b482a8ed9ff8d763f08800902fdf1f02d",
|
||||
"commit": "cd71fd61e4d1c8db758ac0d2e9d1873a5a4ef547",
|
||||
"missing_artifacts": [],
|
||||
"limitations": [
|
||||
"The git commit and dirty flags are generation-time context; release lock is blocked by source changes, while generated evidence artifacts are tracked separately.",
|
||||
@@ -5263,7 +5263,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 32.49,
|
||||
"duration_ms": 33.77,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -5291,7 +5291,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 28.38,
|
||||
"duration_ms": 31.71,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -5314,7 +5314,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 28.39,
|
||||
"duration_ms": 29.59,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -5342,7 +5342,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 28.18,
|
||||
"duration_ms": 29.77,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -5365,7 +5365,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 28.12,
|
||||
"duration_ms": 32.5,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -5393,7 +5393,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 28.24,
|
||||
"duration_ms": 30.06,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -5416,7 +5416,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 29.02,
|
||||
"duration_ms": 35.9,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -5443,7 +5443,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 30.75,
|
||||
"duration_ms": 29.67,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -5466,7 +5466,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 35.6,
|
||||
"duration_ms": 30.52,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -5495,7 +5495,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 31.44,
|
||||
"duration_ms": 30.91,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -6276,49 +6276,43 @@
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-17",
|
||||
"skill_dir": ".",
|
||||
"commit": "7050664b482a8ed9ff8d763f08800902fdf1f02d",
|
||||
"commit": "cd71fd61e4d1c8db758ac0d2e9d1873a5a4ef547",
|
||||
"git_status": {
|
||||
"available": true,
|
||||
"dirty": true,
|
||||
"changed_file_count": 39,
|
||||
"changed_file_count": 15,
|
||||
"generated_dirty": true,
|
||||
"generated_changed_file_count": 34,
|
||||
"source_dirty": true,
|
||||
"source_changed_file_count": 5,
|
||||
"generated_changed_file_count": 15,
|
||||
"source_dirty": false,
|
||||
"source_changed_file_count": 0,
|
||||
"sample": [
|
||||
" M registry/index.json",
|
||||
" M registry/packages/yao-meta-skill.json",
|
||||
" M reports/adaptation_proposals.json",
|
||||
" M reports/adaptation_proposals.md",
|
||||
" M reports/adoption_drift_report.json",
|
||||
" M reports/architecture_maintainability.json",
|
||||
" M reports/architecture_maintainability.md",
|
||||
" M reports/benchmark_reproducibility.json",
|
||||
" M reports/benchmark_reproducibility.md",
|
||||
" M reports/context_budget.json",
|
||||
" M reports/context_budget.md",
|
||||
" M reports/context_budget_summary.json"
|
||||
],
|
||||
"source_sample": [
|
||||
" M scripts/render_evidence_consistency.py",
|
||||
" M scripts/render_review_studio.py",
|
||||
" M scripts/review_studio_actions.py",
|
||||
" M tests/verify_evidence_consistency.py",
|
||||
" M tests/verify_review_studio.py"
|
||||
" M reports/evidence_consistency.json",
|
||||
" M reports/output_execution_runs.json",
|
||||
" M reports/output_execution_runs.md",
|
||||
" M reports/review-studio.html",
|
||||
" M reports/review-studio.json",
|
||||
" M reports/review-viewer.json",
|
||||
" M reports/skill-interpretation.json"
|
||||
],
|
||||
"source_sample": [],
|
||||
"generated_sample": [
|
||||
" M registry/index.json",
|
||||
" M registry/packages/yao-meta-skill.json",
|
||||
" M reports/adaptation_proposals.json",
|
||||
" M reports/adaptation_proposals.md",
|
||||
" M reports/adoption_drift_report.json",
|
||||
" M reports/architecture_maintainability.json",
|
||||
" M reports/architecture_maintainability.md",
|
||||
" M reports/benchmark_reproducibility.json",
|
||||
" M reports/benchmark_reproducibility.md",
|
||||
" M reports/context_budget.json",
|
||||
" M reports/context_budget.md",
|
||||
" M reports/context_budget_summary.json"
|
||||
" M reports/evidence_consistency.json",
|
||||
" M reports/output_execution_runs.json",
|
||||
" M reports/output_execution_runs.md",
|
||||
" M reports/review-studio.html",
|
||||
" M reports/review-studio.json",
|
||||
" M reports/review-viewer.json",
|
||||
" M reports/skill-interpretation.json"
|
||||
],
|
||||
"generated_dirty_prefixes": [
|
||||
"dist/",
|
||||
@@ -6332,11 +6326,11 @@
|
||||
},
|
||||
"summary": {
|
||||
"reproducibility_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"methodology_complete": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"evidence_bundle_sha256": "c31e8bd9e49e60f14344e25ae71dabf911612d9c1ae6aee292ce566c66b88fce",
|
||||
"evidence_bundle_sha256": "b29129730b143a8ee3e8f3976ea953ed7173e0c7de9c4e8a2fc2f4c47635fe15",
|
||||
"source_contract_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
|
||||
"output_case_count": 5,
|
||||
@@ -6356,19 +6350,18 @@
|
||||
"world_class_source_pass_count": 10,
|
||||
"world_class_source_blocked_count": 9,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 5,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 39,
|
||||
"source_tree_dirty": true,
|
||||
"source_changed_file_count": 5,
|
||||
"changed_file_count": 15,
|
||||
"source_tree_dirty": false,
|
||||
"source_changed_file_count": 0,
|
||||
"generated_tree_dirty": true,
|
||||
"generated_changed_file_count": 34
|
||||
"generated_changed_file_count": 15
|
||||
},
|
||||
"public_claim": {
|
||||
"ready": false,
|
||||
"scope": "public benchmark or world-class readiness claim",
|
||||
"blockers": [
|
||||
"release lock is not clean or commit is unavailable",
|
||||
"provider-backed model holdout evidence is incomplete",
|
||||
"human blind-review adjudication is incomplete",
|
||||
"world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)",
|
||||
@@ -6377,12 +6370,12 @@
|
||||
"policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, accepted world-class evidence, and complete source checks."
|
||||
},
|
||||
"release_lock": {
|
||||
"ready": false,
|
||||
"commit": "7050664b482a8ed9ff8d763f08800902fdf1f02d",
|
||||
"ready": true,
|
||||
"commit": "cd71fd61e4d1c8db758ac0d2e9d1873a5a4ef547",
|
||||
"status_scope": "generation-time status before this report is written",
|
||||
"source_changed_file_count": 5,
|
||||
"generated_changed_file_count": 34,
|
||||
"reason": "source files were dirty at generation time"
|
||||
"source_changed_file_count": 0,
|
||||
"generated_changed_file_count": 15,
|
||||
"reason": "only generated evidence artifacts were dirty at generation time"
|
||||
},
|
||||
"evidence_bundle": {
|
||||
"algorithm": "sha256(path,label,exists,artifact_sha256)",
|
||||
@@ -6390,7 +6383,7 @@
|
||||
"existing_count": 25,
|
||||
"missing_count": 0,
|
||||
"missing_paths": [],
|
||||
"sha256": "c31e8bd9e49e60f14344e25ae71dabf911612d9c1ae6aee292ce566c66b88fce"
|
||||
"sha256": "b29129730b143a8ee3e8f3976ea953ed7173e0c7de9c4e8a2fc2f4c47635fe15"
|
||||
},
|
||||
"methodology": {
|
||||
"path": "reports/benchmark_methodology.md",
|
||||
@@ -6463,8 +6456,8 @@
|
||||
"label": "output_execution",
|
||||
"path": "reports/output_execution_runs.json",
|
||||
"exists": true,
|
||||
"bytes": 7966,
|
||||
"sha256": "9d1dbd75c98b75a63c4c7e3ae4175274a9d54e33fd1ca73561deb4dbc0b315ed"
|
||||
"bytes": 7965,
|
||||
"sha256": "db2564dbc622814ae57e8459d2a241b0f76fbf78f00af1d484ca5cdaa3265cae"
|
||||
},
|
||||
{
|
||||
"label": "blind_review",
|
||||
@@ -18049,9 +18042,9 @@
|
||||
"context_budget_tier": "production",
|
||||
"context_budget_limit": 1000,
|
||||
"skill_body_tokens": 797,
|
||||
"other_text_tokens": 1139278,
|
||||
"other_text_tokens": 1139268,
|
||||
"estimated_initial_load_tokens": 990,
|
||||
"estimated_total_text_tokens": 1140075,
|
||||
"estimated_total_text_tokens": 1140065,
|
||||
"deferred_resource_tokens": 515669,
|
||||
"deferred_resource_warn_threshold": 120000,
|
||||
"deferred_resource_dirs": [
|
||||
@@ -20625,7 +20618,7 @@
|
||||
"weekly_curator": {
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-16T21:16:12Z",
|
||||
"generated_at": "2026-06-17",
|
||||
"skill_dir": ".",
|
||||
"decision": "curator-review",
|
||||
"week_id": "2026-W25",
|
||||
@@ -20639,7 +20632,7 @@
|
||||
"top_score": 88,
|
||||
"skill_count": 12,
|
||||
"actionable_portfolio_issue_count": 0,
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"evidence_consistency_ok": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
@@ -20659,7 +20652,7 @@
|
||||
"top_score": 88,
|
||||
"skill_count": 12,
|
||||
"actionable_portfolio_issue_count": 0,
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"evidence_consistency_ok": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
@@ -20912,7 +20905,7 @@
|
||||
"no_route_opportunity_count": 0
|
||||
},
|
||||
"release_state": {
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"evidence_consistency_ok": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4
|
||||
@@ -21090,7 +21083,7 @@
|
||||
"adaptation_proposals": {
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-16T21:16:12Z",
|
||||
"generated_at": "2026-06-17",
|
||||
"skill_dir": ".",
|
||||
"source_patterns": "reports/user_patterns.json",
|
||||
"pattern_count": 5,
|
||||
|
||||
@@ -1005,11 +1005,11 @@
|
||||
"ok": true,
|
||||
"summary": {
|
||||
"reproducibility_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"methodology_complete": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"evidence_bundle_sha256": "c31e8bd9e49e60f14344e25ae71dabf911612d9c1ae6aee292ce566c66b88fce",
|
||||
"evidence_bundle_sha256": "b29129730b143a8ee3e8f3976ea953ed7173e0c7de9c4e8a2fc2f4c47635fe15",
|
||||
"source_contract_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
|
||||
"output_case_count": 5,
|
||||
@@ -1029,15 +1029,15 @@
|
||||
"world_class_source_pass_count": 10,
|
||||
"world_class_source_blocked_count": 9,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 5,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 39,
|
||||
"source_tree_dirty": true,
|
||||
"source_changed_file_count": 5,
|
||||
"changed_file_count": 15,
|
||||
"source_tree_dirty": false,
|
||||
"source_changed_file_count": 0,
|
||||
"generated_tree_dirty": true,
|
||||
"generated_changed_file_count": 34
|
||||
"generated_changed_file_count": 15
|
||||
},
|
||||
"commit": "7050664b482a8ed9ff8d763f08800902fdf1f02d",
|
||||
"commit": "cd71fd61e4d1c8db758ac0d2e9d1873a5a4ef547",
|
||||
"missing_artifacts": [],
|
||||
"limitations": [
|
||||
"The git commit and dirty flags are generation-time context; release lock is blocked by source changes, while generated evidence artifacts are tracked separately.",
|
||||
|
||||
@@ -1009,11 +1009,11 @@
|
||||
"ok": true,
|
||||
"summary": {
|
||||
"reproducibility_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"methodology_complete": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"evidence_bundle_sha256": "c31e8bd9e49e60f14344e25ae71dabf911612d9c1ae6aee292ce566c66b88fce",
|
||||
"evidence_bundle_sha256": "b29129730b143a8ee3e8f3976ea953ed7173e0c7de9c4e8a2fc2f4c47635fe15",
|
||||
"source_contract_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
|
||||
"output_case_count": 5,
|
||||
@@ -1033,15 +1033,15 @@
|
||||
"world_class_source_pass_count": 10,
|
||||
"world_class_source_blocked_count": 9,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 5,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 39,
|
||||
"source_tree_dirty": true,
|
||||
"source_changed_file_count": 5,
|
||||
"changed_file_count": 15,
|
||||
"source_tree_dirty": false,
|
||||
"source_changed_file_count": 0,
|
||||
"generated_tree_dirty": true,
|
||||
"generated_changed_file_count": 34
|
||||
"generated_changed_file_count": 15
|
||||
},
|
||||
"commit": "7050664b482a8ed9ff8d763f08800902fdf1f02d",
|
||||
"commit": "cd71fd61e4d1c8db758ac0d2e9d1873a5a4ef547",
|
||||
"missing_artifacts": [],
|
||||
"limitations": [
|
||||
"The git commit and dirty flags are generation-time context; release lock is blocked by source changes, while generated evidence artifacts are tracked separately.",
|
||||
|
||||
@@ -1004,11 +1004,11 @@
|
||||
"ok": true,
|
||||
"summary": {
|
||||
"reproducibility_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"methodology_complete": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"evidence_bundle_sha256": "c31e8bd9e49e60f14344e25ae71dabf911612d9c1ae6aee292ce566c66b88fce",
|
||||
"evidence_bundle_sha256": "b29129730b143a8ee3e8f3976ea953ed7173e0c7de9c4e8a2fc2f4c47635fe15",
|
||||
"source_contract_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
|
||||
"output_case_count": 5,
|
||||
@@ -1028,15 +1028,15 @@
|
||||
"world_class_source_pass_count": 10,
|
||||
"world_class_source_blocked_count": 9,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 5,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 39,
|
||||
"source_tree_dirty": true,
|
||||
"source_changed_file_count": 5,
|
||||
"changed_file_count": 15,
|
||||
"source_tree_dirty": false,
|
||||
"source_changed_file_count": 0,
|
||||
"generated_tree_dirty": true,
|
||||
"generated_changed_file_count": 34
|
||||
"generated_changed_file_count": 15
|
||||
},
|
||||
"commit": "7050664b482a8ed9ff8d763f08800902fdf1f02d",
|
||||
"commit": "cd71fd61e4d1c8db758ac0d2e9d1873a5a4ef547",
|
||||
"missing_artifacts": [],
|
||||
"limitations": [
|
||||
"The git commit and dirty flags are generation-time context; release lock is blocked by source changes, while generated evidence artifacts are tracked separately.",
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-17",
|
||||
"generated_at": "2026-06-13",
|
||||
"skill_dir": ".",
|
||||
"summary": {
|
||||
"item_count": 21,
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Skill OS 2.0 Blueprint Coverage
|
||||
|
||||
Generated at: `2026-06-17`
|
||||
Generated at: `2026-06-13`
|
||||
|
||||
## Summary
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-16T21:16:12Z",
|
||||
"generated_at": "2026-06-17",
|
||||
"skill_dir": ".",
|
||||
"decision": "curator-review",
|
||||
"week_id": "2026-W25",
|
||||
@@ -15,7 +15,7 @@
|
||||
"top_score": 88,
|
||||
"skill_count": 12,
|
||||
"actionable_portfolio_issue_count": 0,
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"evidence_consistency_ok": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
@@ -35,7 +35,7 @@
|
||||
"top_score": 88,
|
||||
"skill_count": 12,
|
||||
"actionable_portfolio_issue_count": 0,
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"evidence_consistency_ok": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
@@ -288,7 +288,7 @@
|
||||
"no_route_opportunity_count": 0
|
||||
},
|
||||
"release_state": {
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"evidence_consistency_ok": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Weekly SkillOps Curator Report
|
||||
|
||||
Generated at: `2026-06-16T21:16:12Z`
|
||||
Generated at: `2026-06-17`
|
||||
Week: `2026-W25`
|
||||
|
||||
## Summary
|
||||
@@ -13,7 +13,7 @@ Week: `2026-W25`
|
||||
- top_score: `88`
|
||||
- skill_count: `12`
|
||||
- actionable_portfolio_issue_count: `0`
|
||||
- release_lock_ready: `False`
|
||||
- release_lock_ready: `True`
|
||||
- evidence_consistency_ok: `True`
|
||||
- public_world_class_ready: `False`
|
||||
- world_class_pending_count: `4`
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-17",
|
||||
"generated_at": "2026-06-13",
|
||||
"skill_dir": ".",
|
||||
"summary": {
|
||||
"ledger_ready_to_claim_world_class": false,
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# World-Class Claim Guard
|
||||
|
||||
Generated at: `2026-06-17`
|
||||
Generated at: `2026-06-13`
|
||||
|
||||
## Summary
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-17",
|
||||
"generated_at": "2026-06-13",
|
||||
"skill_dir": ".",
|
||||
"summary": {
|
||||
"schema_present": true,
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# World-Class Evidence Intake
|
||||
|
||||
Generated at: `2026-06-17`
|
||||
Generated at: `2026-06-13`
|
||||
|
||||
## Summary
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-17",
|
||||
"generated_at": "2026-06-13",
|
||||
"skill_dir": ".",
|
||||
"decision": "evidence-pending",
|
||||
"ready_to_claim_world_class": false,
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# World-Class Evidence Ledger
|
||||
|
||||
Generated at: `2026-06-17`
|
||||
Generated at: `2026-06-13`
|
||||
|
||||
## Summary
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-17",
|
||||
"generated_at": "2026-06-13",
|
||||
"skill_dir": ".",
|
||||
"summary": {
|
||||
"audit_decision": "continue-iteration",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# World-Class Evidence Plan
|
||||
|
||||
Generated at: `2026-06-17`
|
||||
Generated at: `2026-06-13`
|
||||
|
||||
## Summary
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-17",
|
||||
"generated_at": "2026-06-13",
|
||||
"skill_dir": ".",
|
||||
"summary": {
|
||||
"evidence_item_count": 4,
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# World-Class Evidence Preflight
|
||||
|
||||
Generated at: `2026-06-17`
|
||||
Generated at: `2026-06-13`
|
||||
|
||||
## Summary
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-17",
|
||||
"generated_at": "2026-06-13",
|
||||
"skill_dir": ".",
|
||||
"summary": {
|
||||
"evidence_item_count": 4,
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# World-Class Operator Runbook
|
||||
|
||||
Generated at: `2026-06-17`
|
||||
Generated at: `2026-06-13`
|
||||
|
||||
## Summary
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-17",
|
||||
"generated_at": "2026-06-13",
|
||||
"skill_dir": ".",
|
||||
"decision": "awaiting-submissions",
|
||||
"ready_to_claim_world_class": false,
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# World-Class Submission Review
|
||||
|
||||
Generated at: `2026-06-17`
|
||||
Generated at: `2026-06-13`
|
||||
|
||||
## Summary
|
||||
|
||||
|
||||
Reference in New Issue
Block a user